decision-tree-analysis

Use when building a decision tree model in R and generating feature importance ranking outputs. Supports classification and regression, automatic task detection, parameter validation, model evaluation summaries, and exports of feature-importance tables and figures.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable CLI skill body with clean argument and output documentation. Its main weaknesses are duplicated example/validation blocks and references to missing test-data files that the examples depend on.

Suggestions

Ship the referenced tests/data/dt_sample1.csv, dt_sample2.csv, and dt_sample3.txt files (or remove the Test Data, Quick Examples, and Validation sections that depend on them) so all referenced bundle paths resolve.

Collapse the Validation section's repeated sample commands into a pointer to the Quick Examples, keeping only the output-file verification checklist to remove redundancy.

Add an explicit validate-fix-retry loop (e.g., 'If verification fails or a SKILL_* error appears, consult Common Errors, fix the input/args, and re-run') to strengthen the batch workflow's feedback cycle.

Dimension	Reasoning	Score
Conciseness	The body is efficient and avoids explaining concepts Claude already knows, but the Validation section re-runs the same three sample commands already shown in Quick Examples and appends a nine-line expected-path checklist, and 'Choose the Task Type' restates argument details.	4 / 5
Actionability	Provides a fully executable primary command, a complete arguments table with defaults, copy-paste-ready Rscript examples for the common classification cases, a concrete CSV sample, and exact output file paths.	5 / 5
Workflow Clarity	A clear Minimal Workflow is paired with a verify-files checklist and error-code-to-cause mapping plus no-split remediation, but the validate-fix-retry feedback loop is only implicit for some failure modes rather than spelled out end-to-end.	4 / 5
Progressive Disclosure	The 'Read These Files When Needed' table well-signals one-level-deep references (algorithm.md, cli-guide.md, troubleshooting.md, main.R) that all exist, but the body repeatedly references tests/data/*.csv sample files that are absent from the bundle, leaving navigation partially broken.	4 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states both its trigger conditions and concrete capabilities with comprehensive, specific actions. It could add a few synonyms (rpart, predictive modeling) and a file extension to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—'building a decision tree model in R', 'generating feature importance ranking outputs', 'automatic task detection', 'parameter validation', 'model evaluation summaries', and 'exports of feature-importance tables and figures'—giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'when' ('Use when building a decision tree model in R and generating feature importance ranking outputs') and 'what' ('Supports classification and regression, automatic task detection...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('decision tree model in R', 'feature importance ranking', 'classification', 'regression') but omits common synonyms and extensions such as 'rpart', 'predictive modeling', or '.r'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche—decision tree modeling in R with feature importance exports—so it is distinguishable from adjacent ML skills with minimal trigger conflict.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Data Analysis/decision-tree-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~11 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.